Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors

• URL: http://arxiv.org/abs/2410.14744v1
• Date: Thu, 17 Oct 2024 15:07:53 GMT
• Title: Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors
• Authors: Anthony Sicilia, Malihe Alikhani,
• Abstract summary: Conversation forecasting tasks a model with predicting the outcome of an unfolding conversation. It can be applied in social media moderation to predict harmful user behaviors before they occur. This paper explores what extent model uncertainty can be used as a tool to mitigate potential biases.
• Score: 29.892041865029803
• License:
• Abstract: Conversation forecasting tasks a model with predicting the outcome of an unfolding conversation. For instance, it can be applied in social media moderation to predict harmful user behaviors before they occur, allowing for preventative interventions. While large language models (LLMs) have recently been proposed as an effective tool for conversation forecasting, it's unclear what biases they may have, especially against forecasting the (potentially harmful) outcomes we request them to predict during moderation. This paper explores to what extent model uncertainty can be used as a tool to mitigate potential biases. Specifically, we ask three primary research questions: 1) how does LLM forecasting accuracy change when we ask models to represent their uncertainty; 2) how does LLM bias change when we ask models to represent their uncertainty; 3) how can we use uncertainty representations to reduce or completely mitigate biases without many training data points. We address these questions for 5 open-source language models tested on 2 datasets designed to evaluate conversation forecasting for social media moderation.

Related papers

• Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method [11.794628063040108]
  Multi-Span Question Answering (MSQA) requires models to extract one or multiple answer spans from a given context to answer a question. We propose Answering-Classifying-Correcting (ACC) framework, which employs a post-processing strategy to handle incorrect predictions.
  arXiv  Detail & Related papers  (2024-10-22T08:04:32Z)
• Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecasting [29.892041865029803]
  We propose a new suite of tasks, challenging language models (LMs) to model the uncertainty of others in dialogue. Uniquely, we view interlocutors themselves as forecasters, asking an LM to predict the uncertainty of the interlocutors. While LMs can explain up to 7% variance in the uncertainty of others, we highlight the difficulty of the tasks and room for future work.
  arXiv  Detail & Related papers  (2024-09-23T13:05:25Z)
• Toward Reliable Human Pose Forecasting with Uncertainty [51.628234388046195]
  We develop an open-source library for human pose forecasting, including multiple models, supporting several datasets. We devise two types of uncertainty in the problem to increase performance and convey better trust.
  arXiv  Detail & Related papers  (2023-04-13T17:56:08Z)
• Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement [54.55643652781891]
  Conversational Question Answering (ConvQA) models aim at answering a question with its relevant paragraph and previous question-answer pairs that occurred during conversation multiple times. We propose to filter out inaccurate answers in the conversation history based on their estimated confidences and uncertainties from the ConvQA model. We validate our models, Answer Selection-based realistic Conversation Question Answering, on two standard ConvQA datasets.
  arXiv  Detail & Related papers  (2023-02-10T09:42:07Z)
• Language Models (Mostly) Know What They Know [10.836210010868932]
  We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly. We investigate whether models can be trained to predict "P(IK)", the probability that "I know" the answer to a question, without reference to any particular proposed answer.
  arXiv  Detail & Related papers  (2022-07-11T22:59:39Z)
• Uncertainty estimation of pedestrian future trajectory using Bayesian approximation [137.00426219455116]
  Under dynamic traffic scenarios, planning based on deterministic predictions is not trustworthy. The authors propose to quantify uncertainty during forecasting using approximation which deterministic approaches fail to capture. The effect of dropout weights and long-term prediction on future state uncertainty has been studied.
  arXiv  Detail & Related papers  (2022-05-04T04:23:38Z)
• Learning to Predict Trustworthiness with Steep Slope Loss [69.40817968905495]
  We study the problem of predicting trustworthiness on real-world large-scale datasets. We observe that the trustworthiness predictors trained with prior-art loss functions are prone to view both correct predictions and incorrect predictions to be trustworthy. We propose a novel steep slope loss to separate the features w.r.t. correct predictions from the ones w.r.t. incorrect predictions by two slide-like curves that oppose each other.
  arXiv  Detail & Related papers  (2021-09-30T19:19:09Z)
• Quantifying sources of uncertainty in drug discovery predictions with probabilistic models [0.0]
  Knowing the uncertainty in a prediction is critical when making expensive investment decisions and when patient safety is paramount. Machine learning (ML) models in drug discovery typically provide only a single best estimate and ignore all sources of uncertainty. Probabilistic predictive models (PPMs) can incorporate uncertainty in both the data and model, and return a distribution of predicted values.
  arXiv  Detail & Related papers  (2021-05-18T18:54:54Z)
• Counterfactual Predictions under Runtime Confounding [74.90756694584839]
  We study the counterfactual prediction task in the setting where all relevant factors are captured in the historical data. We propose a doubly-robust procedure for learning counterfactual prediction models in this setting.
  arXiv  Detail & Related papers  (2020-06-30T15:49:05Z)
• Estimating predictive uncertainty for rumour verification models [24.470032028639107]
  We show that uncertainty estimates can be used to filter out model predictions likely to be erroneous. We propose two methods for uncertainty-based instance rejection, supervised and unsupervised.
  arXiv  Detail & Related papers  (2020-05-14T17:42:25Z)
• Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models [110.82452096672182]
  We propose an extension of the Multiple Hypothesis Prediction (MHP) model to handle ambiguous predictions with sequential data. We also introduce a novel metric for ambiguous problems, which is better suited to account for uncertainties.
  arXiv  Detail & Related papers  (2020-03-10T09:15:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.